Home / AI Research / The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation
THAI Research
The Mask Is Not the Object: Volumetric Supervision for 3D Gaussian Segmentation
by yonseiworld · Jeonghwan Cho, Minsu Kim, Junyoung Hong, Seon Joo Kim
3D Gaussian Splatting enables object-level operations on Gaussian primitives, yet existing segmentation methods are largely trained and evaluated through rendered views. This mismatch can produce accurate rendered masks from incomplete 3D selections since alpha-blended feature supervision concentrates learning on dominant contributors while leaving occluded or low-contribution Gaussians weakly supervised. We propose VODA, a plug-and-play supervision objective that exploits local depth structure to group per-pixel contributors and directly supervises all Gaussians in selected depth clusters, bypassing contribution-weighted gradient delivery. To evaluate volumetric completeness, we introduce…
Upvotes32
Comments4
Published15 Nov 2026